| Price from | — | Free |
| Free plan | — | Yes |
| Free trial | — | — |
| Open source | — | — |
| Web | Yes | Yes |
| Windows | Yes | — |
| Linux | Yes | — |
| API | — | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 0 | 4 |
| Spec score · Text-to-Video Generators | 8.0 (#10) | 8.6 (#7) |
| Spec score · AI video generators | 7.2 (#211) | 7.8 (#130) |
| Commercial use | The CogVideoX License requires commercial users to register for a basic commercial license and limits service visits to one million per month under that license. | Yes |
| Image-to-video | Yes | No |
| Integrations | The project lists community integrations including ComfyUI-CogVideoXWrapper, CogStudio, and Xorbits Inference. | Genmo says Mochi can be used with ComfyUI and its blog lists API partners for integrating Mochi 1 into applications without naming them on that page. |
| Maximum video length | 0.1666666667 | 5.4 |
| Purpose | CogVideoX is an open-source video-generation model family for text-to-video and image-to-video generation. | Genmo describes itself as a research lab developing video world models to understand the physical world. |
| Text-to-video | Yes | The Mochi Playground lets users generate videos by describing what they want to see in natural language. |
| Video output | The README lists CogVideoX1.5-5B as supporting 5- or 10-second videos at 16 frames per second. | The help center says videos are MP4 with H.264 encoding and the base model produces 480p video. |
